github-actions[bot] commented on PR #9028: URL: https://github.com/apache/texera/pull/9028#issuecomment-6380179361
<!-- texera-benchmarks-comment --> ## ⚠️ Benchmark changes need a look 🟢 2 better · 🔴 3 worse · ⚪ 10 noise (<±5%) · 0 without baseline > Compared against main `6cfcfb1` benchmarked on **this same runner**, so the delta is largely free of cross-runner hardware noise. The "7d avg" column still reflects the gh-pages dashboard. Treat <±5% as noise unless repeated. [Dashboard](https://apache.github.io/texera/dev/bench/) · [Run](https://github.com/apache/texera/actions/runs/40064549599) | | config | throughput | MB/s | latency | max Δ latest / 7d | |---|---|---:|---:|---:|---:| | 🔴 | bs=10 sw=10 sl=64 | 535 | 0.326 | 18,154/22,396/22,396 us | 🔴 +21.3% / 🔴 +70.5% | | ⚪ | bs=100 sw=10 sl=64 | 1,257 | 0.767 | 78,863/95,070/95,070 us | ⚪ within ±5% / 🟢 -12.4% | | ⚪ | bs=1000 sw=10 sl=64 | 1,485 | 0.907 | 671,571/751,032/751,032 us | ⚪ within ±5% / 🟢 -17.2% | <details><summary>Baseline details</summary> Latest main `6cfcfb1` from same runner | config | metric | PR | latest main | 7d avg | Δ latest | Δ 7d | |---|---|---:|---:|---:|---:|---:| | bs=10 sw=10 sl=64 | throughput | 535 tuples/sec | 619 tuples/sec | 968.33 tuples/sec | -13.6% | -44.8% | | bs=10 sw=10 sl=64 | MB/s | 0.326 MB/s | 0.378 MB/s | 0.591 MB/s | -13.8% | -44.8% | | bs=10 sw=10 sl=64 | p50 | 18,154 us | 14,966 us | 10,646 us | +21.3% | +70.5% | | bs=10 sw=10 sl=64 | p95 | 22,396 us | 23,708 us | 14,120 us | -5.5% | +58.6% | | bs=10 sw=10 sl=64 | p99 | 22,396 us | 23,708 us | 16,498 us | -5.5% | +35.8% | | bs=100 sw=10 sl=64 | throughput | 1,257 tuples/sec | 1,272 tuples/sec | 1,252 tuples/sec | -1.2% | +0.4% | | bs=100 sw=10 sl=64 | MB/s | 0.767 MB/s | 0.777 MB/s | 0.764 MB/s | -1.3% | +0.4% | | bs=100 sw=10 sl=64 | p50 | 78,863 us | 77,398 us | 83,736 us | +1.9% | -5.8% | | bs=100 sw=10 sl=64 | p95 | 95,070 us | 91,367 us | 92,464 us | +4.1% | +2.8% | | bs=100 sw=10 sl=64 | p99 | 95,070 us | 91,367 us | 108,561 us | +4.1% | -12.4% | | bs=1000 sw=10 sl=64 | throughput | 1,485 tuples/sec | 1,474 tuples/sec | 1,321 tuples/sec | +0.7% | +12.4% | | bs=1000 sw=10 sl=64 | MB/s | 0.907 MB/s | 0.9 MB/s | 0.806 MB/s | +0.8% | +12.5% | | bs=1000 sw=10 sl=64 | p50 | 671,571 us | 682,555 us | 811,260 us | -1.6% | -17.2% | | bs=1000 sw=10 sl=64 | p95 | 751,032 us | 756,671 us | 847,636 us | -0.7% | -11.4% | | bs=1000 sw=10 sl=64 | p99 | 751,032 us | 756,671 us | 879,277 us | -0.7% | -14.6% | </details> <details><summary>Raw CSV</summary> ```csv config_idx,batch_size,schema_width,string_len,num_batches,total_ms,total_tuples,total_bytes,tuples_per_sec,mb_per_sec,lat_p50_us,lat_p95_us,lat_p99_us 0,10,10,64,20,374.15,200,128000,535,0.326,18154.14,22395.76,22395.76 1,100,10,64,20,1591.46,2000,1280000,1257,0.767,78862.78,95069.66,95069.66 2,1000,10,64,20,13465.45,20000,12800000,1485,0.907,671570.53,751031.79,751031.79 ``` </details> -- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. To unsubscribe, e-mail: [email protected] For queries about this service, please contact Infrastructure at: [email protected]
